July 27, 2017
6:47 p.m.
Hello all, I'm looking to sample a large dataset for a subset that best covers the space. One way of doing this would be maximum dissimilarity, say as implemented in R as part of caret::maxDissim <https://rdrr.io/cran/caret/man/maxDissim.html>. Is anyone are of similar functionality available as part of a common Python package, perhaps in scikit-learn? Many thanks in advance, Shyam